community pool / model answer

ThinkingCap-Qwen3.6-27B-int4-AutoRound-v1

chat · josefprusa/ThinkingCap-Qwen3.6-27B-int4-AutoRound-v1

6.4 tok/s · model median · 13 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit6.4 tok/smeasured63922.6 GB80,000vllm

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.